← Search

Yuxuan Ning

2 accepted papers

2024

DarkFed: A Data-Free Backdoor Attack in Federated Learning

IJCAI 2024poster

Federated learning (FL) has been demonstrated to be susceptible to backdoor attacks. However, existing academic studies on FL backdoor attacks rely on a high proportion of real clients with main task-related data, which is impractical. In the context of real-world industrial scenarios, even the simp…

2024

MISA: Unveiling the Vulnerabilities in Split Federated Learning

ICASSP 2024accepted

Federated learning (FL) and split learning (SL) are prevailing distributed paradigms in recent years. They both enable shared global model training while keeping data localized on users’ devices. The former excels in parallel execution capabilities, while the latter enjoys low dependence on edge com…

Cited by 0SourceScholar